Related papers: IRIS: Intent Resolution via Inference-time Saccade…
While chain-of-thought (CoT) prompting improves reasoning in large language models, its effectiveness in vision-language models (VLMs) remains limited due to over-reliance on textual cues and memorized knowledge. To investigate the visual…
For machines to effectively assist humans in challenging visual search tasks, they must differentiate whether a human is simply glancing into a scene (navigational intent) or searching for a target object (informational intent). Previous…
Ambiguity performance is a critical criterion in radar sensor design, which indicates the ambiguities arising from multiple target estimation and detection. We considered a requirement-driven selection of OFDM reference signal (RS) patterns…
Unsupervised physical parameter estimation from video lacks a common benchmark: existing methods evaluate on non-overlapping synthetic data, the sole real-world dataset is restricted to single-body systems, and no established protocol…
A fluid reconfigurable intelligent surface (fRIS)-aided integrated sensing and communication (ISAC) system is proposed to enhance multi-target sensing and multi-user communication. Unlike the conventional RIS, the fRIS employs movable…
Large vision-language models (LVLMs) offer a novel capability for performing in-context learning (ICL) in Visual QA. When prompted with a few demonstrations of image-question-answer triplets, LVLMs have demonstrated the ability to discern…
Despite considerable recent progress in Visual Question Answering (VQA) models, inconsistent or contradictory answers continue to cast doubt on their true reasoning capabilities. However, most proposed methods use indirect strategies or…
Large Vision-Language Models (LVLMs) have demonstrated impressive multimodal abilities but remain prone to multilingual object hallucination, with a higher likelihood of generating responses inconsistent with the visual input when utilizing…
Explainability and interpretability of AI models is an essential factor affecting the safety of AI. While various explainable AI (XAI) approaches aim at mitigating the lack of transparency in deep networks, the evidence of the effectiveness…
How people look at visual information reveals fundamental information about themselves, their interests and their state of mind. While previous visual attention models output static 2-dimensional saliency maps, saccadic models aim to…
Optical intelligent reflecting surface (OIRS) offers a new and effective approach to resolving the line-of-sight blockage issue in visible light communication (VLC) by enabling redirection of light to bypass obstacles, thereby dramatically…
Recent work in XAI for eye tracking data has evaluated the suitability of feature attribution methods to explain the output of deep neural sequence models for the task of oculomotric biometric identification. These methods provide saliency…
Video-based Question Answering (Video QA) is a challenging task and becomes even more intricate when addressing Socially Intelligent Question Answering (SIQA). SIQA requires context understanding, temporal reasoning, and the integration of…
Reasoning Segmentation (RS) aims to delineate objects based on implicit text queries, the interpretation of which requires reasoning and knowledge integration. Unlike the traditional formulation of segmentation problems that relies on fixed…
Video text-based visual question answering (Video TextVQA) aims to answer questions by explicitly reading and reasoning about the text involved in a video. Most works in this field follow a frame-level framework which suffers from redundant…
Improving the effectiveness of human-robot interaction requires social robots to accurately infer human goals through robust intention understanding. This challenge is particularly critical in multimodal settings, where agents must…
Many modern online services feature personalized recommendations. A central challenge when providing such recommendations is that the reason why an individual user accesses the service may change from visit to visit or even during an…
Although Large Vision-Language Models (LVLMs) have demonstrated powerful capabilities in interpreting visual information, they frequently produce content that deviates from visual information, leading to object hallucination. To tackle…
Visual Question Answering (VQA) deep-learning systems tend to capture superficial statistical correlations in the training data because of strong language priors and fail to generalize to test data with a significantly different…
Self-attention has become increasingly popular in a variety of sequence modeling tasks from natural language processing to recommendation, due to its effectiveness. However, self-attention suffers from quadratic computational and memory…